arXiv:2602.07065v1 Announce Type: new Abstract: Contactless and non-invasive estimation of mechanical properties of physical media from optical observations is of interest for manifold engineering and biomedical applications, where direct physical measurements are not possible. Conventional approaches to the assessment of image displacement and non-contact material probing typically rely on time-consuming iterative algorithms for non-rigid image registration and constitutive modelling using discretization and iterative numerical solving techniques, such as Finite Element Method (FEM) and Finite Difference Method (FDM), which […]

Ver mais

arXiv:2603.02430v1 Announce Type: new Abstract: A central idea of knowledge distillation is to expose relational structure embedded in the teacher’s weights for the student to learn, which is often facilitated using a temperature parameter. Despite its widespread use, there remains limited understanding on how to select an appropriate temperature value, or how this value depends on other training elements such as optimizer, teacher pretraining/finetuning, etc. In practice, temperature is commonly chosen via grid search or by adopting values […]

Ver mais

The paper by Marek et al (Reproducible brain-wide association studies require thousands of individuals, Nature, 602, 7902, pp 654-660, 2022) came out recently, and caused a bit of a stir in the field for a couple of reasons: First, the title, while an accurate description of the findings of the paper, is bold and lacking just enough qualifiers to quell immediate questions. “Does this imply that fMRI or other measures used in BWAS are lacking intrinsic sensitivity?” “Is […]

Ver mais

arXiv:2603.22364v1 Announce Type: new Abstract: Diffusion models have achieved state-of-the-art performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modifies the sampling trajectory. From a theoretical perspective, diffusion models trained with standard denoising score matching (DSM) are expected to recover the target data distribution, raising the question of why inference-time guidance is necessary in practice. In this work, we ask whether the DSM training objective can be modified in […]

Ver mais

arXiv:2510.16750v3 Announce Type: replace-cross Abstract: We study a variant of the simple hypothesis testing problem where observed samples do not necessarily come from either of the specified distributions, but rather from a close variant of them. In this setting, we require a test that is robust to misspecification and identifies which distribution is closer in Hellinger distance. If the underlying distribution is nearly equidistant from both hypotheses, the problem becomes intractable. Our main result is a lower bound […]

Ver mais

New York, United States, March 3rd, 2026/Chainwire/–Threshold Network, the decentralized blockchain protocol behind tBTC, has introduced an update to its decentralized application featuring an all-in-one Unified Bitcoin App that enables users to route Bitcoin across major chains through a single interface. This new unified routing interface brings minting, redeeming, bridging, tracking, and native BTC swaps into a single application: The Threshold App. Users can now move Bitcoin across ecosystems through a coordinated system, rather than stitching together multiple […]

Ver mais

arXiv:2602.16811v1 Announce Type: new Abstract: Recent advancements in Natural Language Processing and Deep Learning have enabled the development of Large Language Models (LLMs), which have significantly advanced the state-of-the-art across a wide range of tasks, including Question Answering (QA). Despite these advancements, research on LLMs has primarily targeted high-resourced languages (e.g., English), and only recently has attention shifted toward multilingual models. However, these models demonstrate a training data bias towards a small number of popular languages or rely […]

Ver mais

The team behind Kimi.ai (Moonshot AI) just made a significant contribution to the open-source AI infrastructure space. The research team has made a significant contribution to the open-source AI infrastructure space. They released FlashKDA (Flash Kimi Delta Attention), a high-performance CUTLASS-based kernel implementation of the Kimi Delta Attention (KDA) mechanism. The FlashKDA library is available on GitHub under an MIT license. It delivers prefill speedups of 1.72× to 2.22× over the flash-linear-attention baseline on NVIDIA H20 GPUs, and […]

Ver mais

arXiv:2602.13277v1 Announce Type: new Abstract: Mobile data collection using controllable sinks is an effective approach to improve energy efficiency and data freshness in densely deployed wireless sensor networks (WSNs). However, existing path-planning methods are often heuristic-driven and lack the flexibility to adapt to high-level operational objectives under dynamic network conditions. In this paper, we propose ID2P2, a intent-driven diffusion-based path planning framework for jointly addresses rendezvous point selection and mobile data collector (MDC) tour construction in IoT-enabled dense […]

Ver mais

IEEE 802.11be (Wi-Fi 7) extends wireless network capability through wider channels, higher-order modulation, and tri-band operation; however, realised indoor performance is strongly governed by propagation constraints. This study , therefore, presents a controlled empirical assessment of Wi-Fi 7 behaviour in a multi-storey university building, examining throughput and received signal strength across 2.4-, 5-, and 6 GHz bands using a single-link radio propagation measurement. Six experimental scenarios were designed to isolate dominant indoor impairments, including distance variation, wall penetration, […]

Ver mais